EUVIMEDEUVIMED entdecken
Crossref

Large Language Models for Computer-Aided Design Fine Tuned: Dataset and Experiments

Yuewan Sun, Xingang Li, Zhenghui Sha

Journal of Mechanical Design · 01.04.2025 · 147 (4)

DOI: 10.1115/1.4067713 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mechanical Design, online erschienen am 27.02.2025. Verfasst von Yuewan Sun und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the power of large language models (LLMs) in various cross-modal generation tasks, their ability to generate 3D computer-aided design (CAD) models from text remains underexplored due to the scarcity of suitable datasets. Additionally, there is a lack of multimodal CAD datasets that include both reconstruction parameters and text descriptions, which are essential for the quantitative evaluation of the CAD generation capabilities of multimodal LLMs. To address these challenges, we developed a dataset of CAD models, sketches, and image data for representative mechanical components such as gears, shafts, and springs, along with natural language descriptions collected via Amazon Mechanical Turk. By using CAD programs as a bridge, we facilitate the conversion of textual output from LLMs into precise 3D CAD designs. To enhance the text-to-CAD generation capabilities of GPT models and demonstrate the utility of our dataset, we developed a pipeline to generate fine-tuning training data for GPT-3.5. We fine-tuned four GPT-3.5 models with various data sampling strategies based on the length of a CAD program. We evaluated these models using parsing rate and intersection over union (IoU) metrics, comparing their performance to that of GPT-4 without fine-tuning. The new knowledge gained from the comparative study on the four different fine-tuned models provided us with guidance on the selection of sampling strategies to build training datasets in fine-tuning practices of LLMs for text-to-CAD generation, considering the trade-off between part complexity, model performance, and cost.

Förderung

  • National Science Foundation

Zitieren

APA

Sun, Y., Li, X., & Sha, Z. (2025). Large Language Models for Computer-Aided Design Fine Tuned: Dataset and Experiments. Journal of Mechanical Design, 147(4). https://doi.org/10.1115/1.4067713

Vancouver

Sun Y, Li X, Sha Z. Large Language Models for Computer-Aided Design Fine Tuned: Dataset and Experiments. Journal of Mechanical Design. 2025;147(4). doi:10.1115/1.4067713

BibTeX
@article{Sun2025,
  author = {Sun, Yuewan and Li, Xingang and Sha, Zhenghui},
  title = {Large Language Models for Computer-Aided Design Fine Tuned: Dataset and Experiments},
  journal = {Journal of Mechanical Design},
  year = {2025},
  volume = {147},
  number = {4},
  doi = {10.1115/1.4067713}
}
Kostenlos starten →